Insight into Delay Based Reservoir Computing via Eigenvalue Analysis
This provides a theoretical framework for analyzing and optimizing reservoir computing systems, which is incremental as it builds on existing eigenvalue analysis methods.
The paper tackled the problem of understanding the computational capability of delay-based reservoir computing by linking the task-independent memory capacity to the eigenvalue spectrum of the dynamical system, showing that performance is predictable through small signal response analysis. They applied this method to a photonic laser system with feedback, finding optimal performance when eigenvalues have real parts near zero and off-resonant imaginary parts.
In this paper we give a profound insight into the computation capability of delay-based reservoir computing via an eigenvalue analysis. We concentrate on the task-independent memory capacity to quantify the reservoir performance and compare these with the eigenvalue spectrum of the dynamical system. We show that these two quantities are deeply connected, and thus the reservoir computing performance is predictable by analyzing the small signal response of the reservoir. Our results suggest that any dynamical system used as a reservoir can be analyzed in this way. We apply our method exemplarily to a photonic laser system with feedback and compare the numerically computed recall capabilities with the eigenvalue spectrum. Optimal performance is found for a system with the eigenvalues having real parts close to zero and off-resonant imaginary parts.